9 papers
A Complexity Bound for the Kent-Ganeiber-Mardia Sampler for the Bingham Distribution
Sam Power
The Bingham distribution is a family of antipodally symmetric distributions on the unit sphere, characterised by an exponential-of-quadratic change of measure with respect to the u…
Towards practical PDMP sampling: Metropolis adjustments, locally adaptive step-sizes, and NUTS-based time lengths
Augustin Chevallier, Sam Power, Matthew Sutton
Piecewise-Deterministic Markov Processes (PDMPs) hold significant promise for sampling from complex probability distributions. However, their practical implementation is hindered b…
The sharp one-dimensional convex sub-Gaussian comparison constant
Damek Davis, Sam Power
Let be an integrable real random variable with mean zero and two-sided sub-Gaussian tail for all . We determine the smallest consta…
Some aspects of robustness in modern Markov Chain Monte Carlo
Sam Power, Giorgos Vasdekis
Markov Chain Monte Carlo (MCMC) is a flexible approach to approximate sampling from intractable probability distributions, with a rich theoretical foundation and comprising a wealt…
Analysis of Multiple-try Metropolis via Poincaré inequalities
Rocco Caprio, Sam Power, Andi Q. Wang
We study the Multiple-try Metropolis algorithm using the framework of Poincaré inequalities. We describe the Multiple-try Metropolis as an auxiliary variable implementation of a r…
Distributional Training Data Attribution: What do Influence Functions Sample?
Bruno Mlodozeniec, Isaac Reid, Sam Power +4
Randomness is an unavoidable part of training deep learning models, yet something that traditional training data attribution algorithms fail to rigorously account for. They ignore…